yt_dlp/extractor/puls4.py

   1 from .prosiebensat1 import ProSiebenSat1BaseIE
   2 from ..utils import parse_duration, unified_strdate
   3
   4
   5 class Puls4IE(ProSiebenSat1BaseIE):
   6     _VALID_URL = r'https?://(?:www\.)?puls4\.com/(?P<id>[^?#&]+)'
   7     _TESTS = [{
   8         'url': 'http://www.puls4.com/2-minuten-2-millionen/staffel-3/videos/2min2miotalk/Tobias-Homberger-von-myclubs-im-2min2miotalk-118118',
   9         'md5': 'fd3c6b0903ac72c9d004f04bc6bb3e03',
  10         'info_dict': {
  11             'id': '118118',
  12             'ext': 'flv',
  13             'title': 'Tobias Homberger von myclubs im #2min2miotalk',
  14             'description': 'md5:f9def7c5e8745d6026d8885487d91955',
  15             'upload_date': '20160830',
  16             'uploader': 'PULS_4',
  17         },
  18     }, {
  19         'url': 'http://www.puls4.com/pro-und-contra/wer-wird-prasident/Ganze-Folgen/Wer-wird-Praesident.-Norbert-Hofer',
  20         'only_matching': True,
  21     }, {
  22         'url': 'http://www.puls4.com/pro-und-contra/wer-wird-prasident/Ganze-Folgen/Wer-wird-Praesident-Analyse-des-Interviews-mit-Norbert-Hofer-416598',
  23         'only_matching': True,
  24     }]
  25     _TOKEN = 'puls4'
  26     _SALT = '01!kaNgaiNgah1Ie4AeSha'
  27     _CLIENT_NAME = ''
  28
  29     def _real_extract(self, url):
  30         path = self._match_id(url)
  31         content_path = self._download_json(
  32             'http://www.puls4.com/api/json-fe/page/' + path, path)['content'][0]['url']
  33         media = self._download_json(
  34             'http://www.puls4.com' + content_path,
  35             content_path)['mediaCurrent']
  36         player_content = media['playerContent']
  37         info = self._extract_video_info(url, player_content['id'])
  38         info.update({
  39             'id': str(media['objectId']),
  40             'title': player_content['title'],
  41             'description': media.get('description'),
  42             'thumbnail': media.get('previewLink'),
  43             'upload_date': unified_strdate(media.get('date')),
  44             'duration': parse_duration(player_content.get('duration')),
  45             'episode': player_content.get('episodePartName'),
  46             'show': media.get('channel'),
  47             'season_id': player_content.get('seasonId'),
  48             'uploader': player_content.get('sourceCompany'),
  49         })
  50         return info